Metraipolis › archive › dc_0e324eb676a2

Can large language models unlock discrete data in ophthalmic diagnostic reports? — arXiv:2610.00795

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00795
License (as archived)
CC0-1.0
Archived
2026-10-06T13:54:24.272Z
SHA-256 of the archived text
215c1af78f31826eb3bd51d2eea364a01a674baaf9f8810678f291abdb99b1b8
Stable URL of this page
https://metraipolis.com/documento/dc_0e324eb676a2

How to cite

Can large language models unlock discrete data in ophthalmic diagnostic reports? — arXiv:2610.00795 — arXiv (en), https://arxiv.org/abs/2610.00795 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e324eb676a2 (Metraipolis archive dc_0e324eb676a2, sha256 215c1af78f31826eb3bd51d2eea364a01a674baaf9f8810678f291abdb99b1b8)
BibTeX
@misc{dc0e324eb676a2,
  title = {Can large language models unlock discrete data in ophthalmic diagnostic reports? — arXiv:2610.00795},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00795},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e324eb676a2; sha256 215c1af78f31826eb3bd51d2eea364a01a674baaf9f8810678f291abdb99b1b8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00795. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Objective: To assess the accuracy and efficiency of a large language model (LLM) using two prompt strategies to extract structured data from ophthalmic diagnostic PDF reports. Methods: Twenty deidentified reports across four types (Visual Field, OCT Glaucoma Overview, OCT retinal nerve fiber layer Single Exam, and OCT Thickness Map; n = 5 each) were processed using two GPT-4o-assisted pipelines and compared with a reconciled manual ground truth. Schema-Constrained used Structured Output mode with a predefined JSON Schema; Prompt-Only used a detailed instruction prompt followed by Python conversion to JSON. Outcomes were value accuracy, formatting accuracy, and extraction time. Results: Schema-Constrained value accuracy was 100.00% for Visual Field and RNFL Single Exam, 97.45% for Glaucoma Overview, and 98.00% for Thickness Map; Prompt-Only achieved 100.00% across all four report types. Formatting accuracy was 100.00% for Schema-Constrained across all report types and 100.00% for Prompt-Only except RNFL Single Exam (90.14%). Mean extraction time was 56.51 s per report for manual review versus 5.04 s for Schema-Constrained and 4.70 s for Prompt-Only, an approximately 92% reduction. Conclusions: In this small proof-of-concept dataset, general-purpose LLM-assisted pipelines extracted structured data from ophthalmic diagnostic PDFs with high accuracy and substantially reduced processing time. Prompt-Only achieved the highest value accuracy, while Schema-Constrained produced schema-compliant output with 100% formatting accuracy. These complementary strengths support further evaluation of hybrid, validation-aware workflows for research and clinical data abstraction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.00795 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T12:15:34.647Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).